Non-proliferative diabetic retinopathy symptoms detection and classification using neural network.

Diabetic retinopathy (DR) causes blindness in the working age for people with diabetes in most countries. The increasing number of people with diabetes worldwide suggests that DR will continue to be major contributors to vision loss. Early detection of retinopathy progress in individuals with diabetes is critical for preventing visual loss. Non-proliferative DR (NPDR) is an early stage of DR. Moreover, NPDR can be classified into mild, moderate and severe. This paper proposes a novel morphology-based algorithm for detecting retinal lesions and classifying each case. First, the proposed algorithm detects the three DR lesions, namely haemorrhages, microaneurysms and exudates. Second, we defined and extracted a set of features from detected lesions. The set of selected feature emulates what physicians looked for in classifying NPDR case. Finally, we designed an artificial neural network (ANN) classifier with three layers to classify NPDR to normal, mild, moderate and severe. Bayesian regularisation and resilient backpropagation algorithms are used to train ANN. The accuracy for the proposed classifiers based on Bayesian regularisation and resilient backpropagation algorithms are 96.6 and 89.9, respectively. The obtained results are compared with results of the recent published classifier. Our proposed classifier outperforms the best in terms of sensitivity and specificity.

An intelligent decision support system for quantitative assessment of gastric atrophy.

AIMS: To build an automated decision support system to assist pathologists in grading gastric atrophy according to the updated Sydney system. METHODS: A database of 143 biopsies was used to train and examine the proposed system. A panel of three experienced pathologists reached a consensus regarding the grading of the studied biopsies using the visual scale of the updated Sydney system. Digital imaging techniques were utilised to extract a set of discriminating morphological features that describe each atrophy grade sufficiently and uniquely. A probabilistic neural networks structure was used to build a grading system. To evaluate the performance of the proposed system, 66% of the biopsies (94 biopsy images) were used for training purposes and 34% (49 biopsy images) were used for testing and validation purposes. RESULTS: During the training phase, a 98.9% precision was achieved, whereas during testing, a precision of 95.9% was achieved. The overall precision achieved was 97.9%. CONCLUSIONS: A fully automated decision support system to grade gastric atrophy according to the updated Sydney system is proposed. The system utilises advanced image processing techniques and probabilistic neural networks in conducting the assessment. The proposed system eliminates inter- and intra-observer variations with high reproducibility.